RichardForests (Richrich)

upvoted an article 4 months ago

Article

Open-source DeepResearch – Freeing our search agents

By

and 4 others •

Feb 4

• 1.25k

upvoted a paper 5 months ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published Nov 4, 2024 • 52

upvoted an article 6 months ago

Article

Merge Large Language Models with mergekit

By

•

Jan 9, 2024

• 120

upvoted a collection 6 months ago

xLAM models

Collection

xLAM: A Family of Large Action Models to Empower AI Agent Systems: https://github.com/SalesforceAIResearch/xLAM • 21 items • Updated Apr 18 • 49

upvoted a paper 6 months ago

StreamChat: Chatting with Streaming Video

Paper • 2412.08646 • Published Dec 11, 2024 • 18

upvoted 3 articles 6 months ago

Article

Better RAG 3: The text is your friend

By

•

Mar 14, 2024

• 9

Article

Better RAG 2: Single-shot is not good enough

By

•

Mar 14, 2024

• 15

Article

Better RAG 1: Advanced Basics

By

•

Mar 14, 2024

• 29

upvoted a paper 6 months ago

Star Attention: Efficient LLM Inference over Long Sequences

Paper • 2411.17116 • Published Nov 26, 2024 • 55

upvoted 2 collections 6 months ago

MoE_Papers

Collection

4 items • Updated Dec 25, 2024 • 1

LLM

Collection

47 items • Updated 9 days ago • 1

upvoted 2 papers 6 months ago

Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation

Paper • 2402.10210 • Published Feb 15, 2024 • 36

Hydragen: High-Throughput LLM Inference with Shared Prefixes

Paper • 2402.05099 • Published Feb 7, 2024 • 20

upvoted an article 6 months ago

Article

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

By

•

May 7, 2024

• 82

upvoted a paper 7 months ago

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

Paper • 2210.14986 • Published Oct 26, 2022 • 5

upvoted a paper 11 months ago

KAN or MLP: A Fairer Comparison

Paper • 2407.16674 • Published Jul 23, 2024 • 44

upvoted an article 11 months ago

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

By

and 4 others •

May 24, 2023

• 151

upvoted 3 papers 12 months ago

Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models

Paper • 2406.13099 • Published Jun 18, 2024 • 4

ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning

Paper • 2406.14130 • Published Jun 20, 2024 • 10

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

Paper • 2406.11896 • Published Jun 14, 2024 • 20

Richrich

AI & ML interests

Organizations

RichardForests's activity

Open-source DeepResearch – Freeing our search agents

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Merge Large Language Models with mergekit

xLAM models

StreamChat: Chatting with Streaming Video

Better RAG 3: The text is your friend

Better RAG 2: Single-shot is not good enough

Better RAG 1: Advanced Basics

Star Attention: Efficient LLM Inference over Long Sequences

MoE_Papers

LLM

Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation

Hydragen: High-Throughput LLM Inference with Shared Prefixes

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

KAN or MLP: A Fairer Comparison

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models

ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning